Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 65k
    5. 20-GEMMASCOPE-RES-65K
    6. 765
    Prev
    Next
    INDEX
    Explanations

    elements related to rituals, offerings, and communication with ancestral spirits

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    references to deals or bargains involving one's soul

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    soul of

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_65k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     transparent
    -0.49
    pha
    -0.44
    发表于
    -0.43
     transparency
    -0.42
     gouvernements
    -0.42
     Transparency
    -0.42
    StateChange
    -0.41
     Transparen
    -0.41
     Alpha
    -0.41
     ThemeData
    -0.41
    POSITIVE LOGITS
     soul
    1.64
     souls
    1.62
    soul
    1.35
     Soul
    1.28
    Soul
    1.22
     SOUL
    1.19
     Souls
    1.18
     âme
    1.14
    Souls
    1.07
     spirit
    0.95
    Activations Density 0.058%

    No Known Activations